Home > OS >  Inconsistent number of samples error in SVM accuracy calculation
Inconsistent number of samples error in SVM accuracy calculation

Time:10-20

I'm trying to calculate the accuracy score, of a SVM using Laplacian kernel (as a pre-computed kernel). However, I'm getting the error as below when I try to calculate the accuracy score.

My code :

import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score
from sklearn.svm import SVC
from sklearn.metrics.pairwise import laplacian_kernel

#Load the iris data
iris_data = load_iris()

#Split the data and target
X = iris_data.data
y = iris_data.target

#Convert X and y to a numpy array
X = np.array(X)
y = np.array(y)

#Perform train-test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42, shuffle=True)

#Using Laplacian kernel - https://scikit-learn.org/stable/modules/metrics.html#laplacian-kernel
K = np.array(laplacian_kernel(X_train, gamma=.5))
svm = SVC(kernel='precomputed').fit(K, np.ravel(y_train))
pred_y = svm.predict(K)

#Print accuracy score - here is where the error is happening.
print(accuracy_score(y_test, pred_y))

When I run this code, I'm getting error as shown below :

Traceback (most recent call last):
  File "/Users/user/Desktop/Research/Src/Laplace.py", line 36, in <module>
    print(accuracy_score(y_test, pred_y))
  File "/Users/user/miniforge3/envs/user_venv/lib/python3.8/site-packages/sklearn/utils/validation.py", line 63, in inner_f
    return f(*args, **kwargs)
  File "/Users/user/miniforge3/envs/user/lib/python3.8/site-packages/sklearn/metrics/_classification.py", line 202, in accuracy_score
    y_type, y_true, y_pred = _check_targets(y_true, y_pred)
  File "/Users/user/miniforge3/envs/user/lib/python3.8/site-packages/sklearn/metrics/_classification.py", line 83, in _check_targets
    check_consistent_length(y_true, y_pred)
  File "/Users/user/miniforge3/envs/user/lib/python3.8/site-packages/sklearn/utils/validation.py", line 262, in check_consistent_length
    raise ValueError("Found input variables with inconsistent numbers of"
ValueError: Found input variables with inconsistent numbers of samples: [45, 105]

So how can I resolve this error?

CodePudding user response:

You calculated pred_y using your train inputs which has 105 elements and y_test has 45 elements.

You need to add a step:

#user3046211's code

import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score
from sklearn.svm import SVC
from sklearn.metrics.pairwise import laplacian_kernel

#Load the iris data
iris_data = load_iris()

#Split the data and target
X = iris_data.data
y = iris_data.target

#Convert X and y to a numpy array
X = np.array(X)
y = np.array(y)

#Perform train-test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42, shuffle=True)

#Using Laplacian kernel - https://scikit-learn.org/stable/modules/metrics.html#laplacian-kernel
K = np.array(laplacian_kernel(X_train, gamma=.5))
svm = SVC(kernel='precomputed').fit(K, np.ravel(y_train))
pred_y = svm.predict(K)

#Print accuracy score - here is where the error is happening.
print(accuracy_score(y_test, pred_y))

# NEW CODE STARTS HERE
K_test = np.array(laplacian_kernel(X=X_test,Y=X_train, gamma=.5))
pred_y_test = svm.predict(K_test)
print(accuracy_score(y_test, pred_y_test))
  • Related